Journal Publications

[23] Qian Zhao, Xiangyu Rui, Zhi Han and Deyu Meng. Multilinear multitask learning by rank-product regularization. Accepted by IEEE Transactions on Neural Networks and Learning Systems, 2019.

[22] Zongsheng Yue, Hongwei Yong, Deyu Meng, Qian Zhao, Yee Leung and Lei Zhang. Robust multi-view subspace learning with non-independently and non-identically distributed complex noise. Accepted by IEEE Transactions on Neural Networks and Learning Systems, 2019.

[21] Jing Yao, Deyu Meng, Qian Zhao, Wenfei Cao and Zongben XuNonconvex-sparsity and nonlocal-smoothness based blind hyperspectral unmixingIEEE Transactions on Image Processing, 28(6):2991-3006, 2019. 

[20] Xi’ai Chen, Zhi Han, Yao Wang, Qian Zhao, Deyu Meng, Lin Lin and Yandong Tang. A generalized model for robust tensor factorization with noise modeling by mixture of GaussiansIEEE Transactions on Neural Networks and Learning Systems, 29(11):5380-5393, 2018.

[19] Zongsheng Yue, Deyu Meng, Yongqing Sun and Qian Zhao. Hyperspectral image estoration under complex multi-band noises. Remote Sensing, 10(10):1631, 2018.

[18] Qi Xie, Qian Zhao, Deyu Meng and Zongben Xu. Kronecker-basis-representation based tensor sparsity and its applications to tensor recovery. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(8):1888-1902, 2018.

[17] Chenqiang Gao, Lan Wang, Yongxing Xiao, Qian Zhao and Deyu Meng. Infrared small-dim target detection based on Markov random field guided noise modeling. Pattern Recognition, 76:463-475, 2018.

[16] Yao Wang, Jiangjun Peng, Qian Zhao, Deyu Meng, Yee Leung and Xi-Le Zhao. Hyperspectral image restoration via total variation regularized low-rank tensor decomposition. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(4):1227-1243, 2018.

[15] Yang Chen, Xiangyong Cao, Qian Zhao, Deyu Meng and Zongben Xu. Denoising hyperspectral image with non-i.i.d. noise structure. IEEE Transactions on Cybernetics, 48(3):1054-1066, 2018.

[14] Jing Yao*, Xiangyong Cao*, Qian Zhao, Deyu Meng and Zongben Xu. Robust subspace clustering via penalized mixture of GaussiansNeurocomputing, 278:4-11, 2018.  (*Contributed equally)

[13] Yao Wang, Lin Lin, Qian Zhao, Tianwei Yue, Deyu Meng and Yee Leung. Compressive Sensing of Hyperspectral Images via Joint Tensor Tucker Decomposition and Weighted Total Variation regularization. IEEE Geoscience and Remote Sensing Letters, 14(12):2457-2461, 2017.

[12] Qi Xie, Dong Zeng, Qian Zhao, Jianhua Ma, Zongben Xu, Zhenrong Liang and Deyu Meng. Robust low-dose CT sinogram prepocessing via exploiting noise-generating mechanism. IEEE Transactions on Medical Imaging, 36(12):2487-2498, 2017.

[11] Deyu Meng, Qian Zhao and Lu Jiang. A theoretical understanding of self-paced learning. Information Sciences, 414:319-328, 2017.

[10] Xiangyong Cao, Lin Xu, Deyu Meng, Qian Zhao and Zongben Xu. Integration of 3-dimensional discrete wavelet transform and Markov random field for hyperspectral image classificationNeurocomputing, 226:90-100, 2017.

[9]   Xiangyong Cao, Qian Zhao, Deyu Meng, Yang Chen and Zongben Xu. Robust low-rank matrix factorization under general mixture noise distributionsIEEE Transactions on Image Processing, 25(10):4677-4690, 2016.

[8]   Lingling Wang, Qian Zhao, Jinghuai Gao, Zongben Xu, Michael Fehler and Xiudi Jiang. Seismic sparse-spike deconvolution via Toeplitz-sparse matrix factorization. Geophysics, 81(2):169-182, 2016.

[7]   Tieliang Gong, Qian Zhao, Deyu Meng and Zongben Xu. Why curriculum learning & self-paced learning work in big/noisy data: a theoretical perspective. Big Data and Information Analytics, 1(1):111-127, 2016.

[6]   Qian Zhao, Deyu Meng, Zongben Xu, Wangmeng Zuo and Yan Yan. L1-norm low-rank matrix factorization by variational Bayesian method. IEEE Transactions on Neural Networks and Learning Systems, 26(4):825-839, 2015.

[5]   Qian Zhao, Deyu Meng, Zongben Xu and Chenqiang Gao. A block coordinate descent approach for sparse principal component analysis. Neurocomputing, 153:180-190, 2015.

[4]   Qian Zhao, Deyu Meng and Zongben Xu. Robust sparse principal component analysis. SCIENCE CHINA Information Sciences, 57:092115(14), 2014.

[3]   Deyu Meng, Qian Zhao, Yee Leung and Zongben Xu. Learning dictionary from signals under global sparsity constraint. Neurocomputing, 119:308-318, 2013.

[2]   Deyu Meng, Qian Zhao and Zongben Xu. Improve robustness of sparse PCA by L1-norm maximization. Pattern Recognition, 45(1):487-497, 2012.

[1]   Qian Zhao, Deyu Meng and Zongben Xu. L1/2 regularized logistic regression. Pattern Recognition and Artifical Intelligence (In Chinese), 25(5):721-728, 2012.

Conference Publications

[12] Qi Xie, Minghao Zhou, Qian Zhao, Deyu Meng, Wangmeng Zuo and Zongben Xu. Multispectral and hyperspectral image fusion by MS/HS fusion netIn: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019.

[11] Wei Wei, Deyu Meng, Qian Zhao, Cheng Wu and Zongben Xu. Semi-supervised transfer learning for image rain removalIn: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Long Beach, USA, 2019. 

[10] Minghan Li, Qi Xie, Qian Zhao, Wei Wei, Shuhang Gu, Jing Tao and Deyu Meng. Video rain streak removal by multiscale convolutional sparse coding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018.

[9]   Wei Wei, Lixuan Yi, Qi Xie, Qian Zhao, Deyu Meng and Zongben Xu. Should we encode rain streaks in video as deterministic or stochastic? In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017.

[8]   Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu, Shuhang Gu, Wangmeng Zuo and Lei Zhang. Multispectral images denoising by intrinsic tensor sparsity regularization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016.

[7]   Xi’ai Chen, Zhi Han, Yao Wang, Qian Zhao, Deyu Meng and Yandong Tang. Robust tensor factorization with unknown noiseIn: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016.

[6]   Qian Zhao, Deyu Meng, Xu Kong, Qi Xie, Wenfei Cao, Yao Wang and Zongben Xu. A novel sparsity measure for tensor recovery. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015.

[5]   Xiangyong Cao, Yang Chen, Qian Zhao, Deyu Meng, Yao Wang, Dong Wang and Zongben Xu. Low-rank matrix factorization under general mixture noise distributions. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015.

[4]   Dingwen Zhang, Deyu Meng, Chao Li, Lu Jiang, Qian Zhao and Junwei Han. A self-paced multiple-instance learning framework for co-saliency detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015.

[3]   Qian Zhao, Deyu Meng, Lu Jiang, Qi Xie, Zongben Xu and Alexander Hauptmann. Self-paced learning for matrix factorization. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), Austin, USA, 2015.

[2]   Lu Jiang, Deyu Meng, Qian Zhao, Shiguang Shan and Alexander Hauptmann. Self-paced curriculum learning. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), Austin, USA, 2015.

[1]   Qian Zhao, Deyu Meng, Zongben Xu, Wangmeng Zuo and Lei Zhang. Robust principal component analysis with complex noise. In: Proceedings of the 31st International Conference on Machine Learning (ICML), Beijing, China, 2014. 

Technical Reports

[1] Deyu Meng, Qian Zhao and Lu Jiang. What Objective Does Self-paced Learning Indeed Optimize? arXiv:1511.06049, 2015.